{"affected":[{"package":{"ecosystem":"Hex","name":"ash_ai","purl":"pkg:hex/ash_ai"},"ranges":[{"events":[{"introduced":"0.1.0"},{"fixed":"1.0.0"}],"type":"SEMVER"}],"versions":["0.1.0","0.1.1","0.1.3","0.1.4","0.1.5","0.1.6","0.1.7","0.1.8","0.1.9","0.1.10","0.1.11","0.2.0","0.2.1","0.2.2","0.2.3","0.2.4","0.2.5","0.2.6","0.2.7","0.2.8","0.2.9","0.2.10","0.2.11","0.2.12","0.2.13","0.2.14","0.3.0","0.4.0","0.5.0","0.6.0","0.6.1","0.7.0","0.7.1","0.7.2","0.7.3","0.8.0","0.8.1","0.8.2"]},{"ranges":[{"events":[{"introduced":"4aab131d40a0bd5a8cf0b3c4eaaa59d49565f3d1"},{"fixed":"e9948254b5659c1143b73dc2f59f457931e64514"}],"repo":"https://github.com/ash-project/ash_ai","type":"GIT"}]}],"aliases":["GHSA-2g59-hg7m-qc83","CVE-2026-77956"],"credits":[{"name":"Peter Ullrich","type":"FINDER"},{"name":"Peter Ullrich","type":"REPORTER"},{"name":"Zach Daniel / Ash Project","type":"REMEDIATION_DEVELOPER"},{"name":"Jonatan Männchen / EEF","type":"COORDINATOR"}],"database_specific":{"capec_ids":["CAPEC-242"],"cpe_ids":["cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:*"],"cwe_ids":["CWE-94"]},"details":"## Summary\n\nImproper Control of Generation of Code (Code Injection) vulnerability in ash-project ash\\_ai allows a remote, unauthenticated client to execute arbitrary Elixir code.\n\nAshAi.Actions.Prompt evaluates prompt content through EEx.eval\\_string/2. The documented prompt: fn input, context -> ... end form lets the prompt content be built from action arguments, so when a prompt action's text incorporates request data, that attacker-controlled text is compiled and run as an EEx template (Elixir source). Content such as <%= System.cmd(...) %> therefore executes on the server before any model request is made, requiring no authentication beyond reaching a prompt action. The fix stops evaluating function-supplied prompt content as EEx; only statically configured templates are evaluated.\n\nThis issue affects ash\\_ai: from 0.1.0 before 1.0.0.","id":"EEF-CVE-2026-77956","modified":"2026-08-31T00:56:26.781104Z","published":"2026-08-31T00:56:26.440Z","references":[{"type":"ADVISORY","url":"https://github.com/ash-project/ash_ai/security/advisories/GHSA-2g59-hg7m-qc83"},{"type":"WEB","url":"https://cna.erlef.org/cves/CVE-2026-77956.html"},{"type":"FIX","url":"https://github.com/ash-project/ash_ai/commit/e9948254b5659c1143b73dc2f59f457931e64514"},{"type":"PACKAGE","url":"https://hex.pm/packages/ash_ai"}],"related":[],"schema_version":"1.7.3","severity":[{"score":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H","type":"CVSS_V4"}],"summary":"EEx template evaluation of prompt content in AshAi enables remote code execution","upstream":[]}